Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112123
    Prev
    Next
    INDEX
    Explanations

    debe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Question
    -0.09
     Oak
    -0.08
    found
    -0.08
     любых
    -0.08
    printed
    -0.08
    _wall
    -0.08
    LN
    -0.07
     Mount
    -0.07
    -wall
    -0.07
    -Paul
    -0.07
    POSITIVE LOGITS
     RDC
    0.08
     promoção
    0.08
     আপন
    0.08
     umo
    0.07
     secretaria
    0.07
     Ras
    0.07
     ị
    0.07
    בודה
    0.07
     humano
    0.07
     satisfactor
    0.07
    Activations Density 0.005%

    No Known Activations